• Journal of Digital Convergence
• /
• v.11 no.3
• /
• pp.127-138
• /
• 2013

The age of social network has arrived. Social media is the various online media for sharing of opinions and experiences and open for internet users' participation. As the new communication tools, social media has been in the limelight, threatening the traditional media as alternative media. In globalization, country image is seen as the source of competitiveness of a country. The goal of this study is to examine what impact does the utilization of social media has on country image, and we conducted our analysis in two aspects of social media utilization, usage volume and usage diversity. In addition, we examined the impact of factors that form the country image on purchase intention. The analytical results show that media usage volume positively affects country image, people image, political image and media usage diversity has significant effects on economical image, people image and political image.

• The KIPS Transactions:PartB
• /
• v.11B no.5
• /
• pp.573-580
• /
• 2004

As the modern techniques have improved, people intend to store and manage the information on the web. Especially, it is the image data that is given a great deal of weight of the information because of the development of the scan and popularization of the digital camera and the cell-phone's camera. However, most image retrieval systems are still based on the text annotations while many images are creating everyday on the web. In this paper, we suggest the new approach for the semantic image retrieval using the RDF metadata based on the representation of the spatial relationships. For the semantic image retrieval, firstly we define the new vocabularies to represent the spatial relationships between the objects in the image. Secondly, we write the metadata about the image using RDF and new vocabularies. Finally. we could expect more correct result in our image retrieval system.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1509-1516
• /
• 2017

In first-person perspective training system, the users needs realistic experience. For providing this experience, the system should offer the users virtual and real images at the same time. We propose an automatic a persons's arm segmentation and image composition method. It consists of arm segmentation part and image composition part. Arm segmentation uses an arbitrary image as input and outputs arm segment or alpha matte. It enables end-to-end learning because we make use of FCN in this part. Image composition part conducts image combination between the result of arm segmentation and other image like road, building, etc. To train the network in arm segmentation, we used arm images through dividing the videos that we took ourselves for the training data.

• Journal of Digital Convergence
• /
• v.12 no.10
• /
• pp.353-361
• /
• 2014

This study was confirmed nurse's traditional, social, professional and personal image of the dimensional perception of the difference between the majors and non-majors students exist? and Reflected on the role of the media image of nurses are there differences in perception? and Nurses and nurse related information, and information on contacting the media and contacted the media image of the existing research results and is there a difference? For the purpose, we survey the nursing majors and non-majors students. The results follows. First, the traditional nurses, social, professional and personal image perception gap is high. Second, the media reflected the image of the nurse in charge of the secondary role of a doctor about the image is high. Third, the nurse contacted the media about the TV is very high. The results of this study have implications to enable communication between patients and nurses agree that will provide evidence. In particular, the nurses through the use of media(PPL and Publicity strategy) suggest ways to improve the image.

• Journal of KIISE
• /
• v.43 no.1
• /
• pp.47-53
• /
• 2016

While the Internet develops rapidly, a huge amount of image data collected from smart phones, digital cameras and black boxes are being shared through social media sites. Generally, social images are handled by tagging them with information. Due to the ease of sharing multimedia and the explosive increase in the amount of tag information, it may be considered too much hassle by some users to put the tags on images. Image retrieval is likely to be less accurate when tags are absent or mislabeled. In this paper, we suggest a method of extracting tags from social images by using image content. In this method, CNN(Convolutional Neural Network) is trained using ImageNet images with labels in the training set, and it extracts labels from instagram images. We use the extracted labels for automatic image tagging. The experimental results show that the accuracy is higher than that of instagram retrievals.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.65-70
• /
• 2013

Recently, the field of computer vision has been actively researched through digital image which can be easily generated as the development and expansion of digital camera technology. Especially, research that extracts and utilizes the feature in image has been actively carried out. The image stitching is a method that creates the high resolution image using features extract and match. Image stitching can be widely used in military and medical purposes as well as in variety fields of real life. In this paper, we have proposed efficient image stitching method using fast feature descriptor extraction and matching based on SURF algorithm. It can be accurately, and quickly found matching point by reduction of dimension of feature descriptor. The feature descriptor is generated by classifying of unnecessary minutiae in extracted features. To reduce the computational time and efficient match feature, we have reduced dimension of the descriptor and expanded orientation window. In our results, the processing time of feature matching and image stitching are faster than previous algorithms, and also that method can make natural-looking stitched image.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.32-38
• /
• 2021

Image classification through deep learning on the image from photographs has been a very active research field for the past several years. In this paper, we propose a method of automatically discriminating stone images from domestic source through deep learning, which is to use Python's hash library to scan 300×300 pixel photo images of granites such as Hwangdeungseok, Goheungseok, and Pocheonseok, performing data preprocessing to create learning images by examining duplicate images for each stone, removing duplicate images with the same hash value as a result of the inspection, and deep learning by stone. In addition, to utilize VGGNet, the size of the images for each stone is resized to 224×224 pixels, learned in VGG16 where the ratio of training and verification data for learning is 80% versus 20%. After training of deep learning, the loss function graph and the accuracy graph were generated, and the prediction results of the deep learning model were output for the three kinds of stone images.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.465-468
• /
• 2023

디퓨전 모델에서 생성한 이미지를 조작하는 기존 프롬프트 기반 방법과 포인트 기반 방법에는 각각의 단점이 있다. 프롬프트 기반은 프롬프트로만 조작이 가능하고 세세하지 못하다. 포인트 기반은 입력 이미지의 스타일을 보존하려면 파인튜닝이 필요하다. 본 논문은 디퓨전 생성 모델에 셀프 어텐션 제어와 드래그 조작을 통해, 파라미터 학습 없이, 이미지의 스타일을 보존하며 다양한 범위의 이미지 조작이 가능한 방법을 제안한다.

• Journal of Korea Multimedia Society
• /
• v.11 no.2
• /
• pp.206-213
• /
• 2008

Animation are consist of consecutive various images, and there are figure and ground. The value of figure image as character in animation consider more significant than the background image, it can be detected many literature reviews on that subject. It, however, is also a critical element for completing animation, in reality, it is not found many academical achievements on this subject. The background images imply the information of environment and atmosphere, and elucidates where the story happen, therefore character move, talk and express themselves there. In terms of academic endeavour to extend the knowledge on animation, this paper is one of vital researches to be suggest on background image study. The main purpose of this study is to classify the background images in the ways of three categories such as painting concepts of concrete, semi-abstract, and abstract to camera concept of deep-focus, out-focus, and distortion. It is to instigate for the study of background images, in the practical view. And it will be utilizing the basic theories of cognitive psychology, painting and camera techniques, in the ways of It is analysed to frequency of use, reality, amount of information, perspective, and role of background image. This study is to provide a basic theory of visual classification on background image for practicing animations and researching on this subject.

• Journal of the Korea Society of Computer and Information
• /
• v.6 no.2
• /
• pp.65-69
• /
• 2001

Edge detection is the most important process that belongs to the first step in image recognition or vision system and can determine the efficiency valuation. The edge detection with color images is very difficult. because color images have lots of information that contain not only general information representing shape, brightness and so on but also that representing colors. In this paper, we propose architecture of universalized Color Morphological Pyramids(CMP) which is able to give effective edge detection. Image pyramid architecture is a successive image sequence whose area ratio 2$\^$-1/(ι= 1, 2, . . . ,N) after filtering and subsampling of input image. In this technique, noise removed by sequential filtering and resolution is degraded by downsampling using CMP in various color spaces. After that, new level images are constructed that apply formula using distance of neighbor vectors in close level images and detection its image.